Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with multi-frame spatial understanding by integrating fundamental spatial skills, including depth perception, visual correspondence, and dynamic perception. We design a novel data pipeline and collect the MultiSPA dataset of more than 27 million samples spanning diverse 3D and 4D scenes to enable training. Alongside MultiSPA, we introduce a comprehensive benchmark that tests a wide spectrum of spatial tasks under uniform metrics. Our resulting model, Multi-SpatialMLLM, achieves significant gains over baselines and proprietary systems, demonstrating scalable and generalizable multi-frame perception. We further observe multi-task benefits and emergent spatial capabilities in challenging scenarios, and showcase how our model can serve as a multi-frame reward annotator for robotics.

We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.

Efficiently reconstructing 3D scenes from monocular video remains a core challenge in computer vision, vital for applications in virtual reality, robotics, and scene understanding. Recently, frame-by-frame progressive reconstruction without camera poses is commonly adopted, incurring high computational overhead and compounding errors when scaling to longer videos. To overcome these issues, we introduce VideoLifter, a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis, achieving both extreme efficiency and SOTA quality. Locally, VideoLifter leverages learnable 3D priors to register fragments, extracting essential information for subsequent 3D Gaussian initialization with enforced inter-fragment consistency and optimized efficiency. Globally, it employs a tree-based hierarchical merging method with key frame guidance for inter-fragment alignment, pairwise merging with Gaussian point pruning, and subsequent joint optimization to ensure global consistency while efficiently mitigating cumulative errors. This approach significantly accelerates the reconstruction process, reducing training time by over 82 % while achieving better visual quality than SOTA methods.

We introduce SAM 3D Body (3DB), a promptable model for single-image full-body 3D human mesh recovery (HMR) that demonstrates state-of-the-art performance, with strong generalization and consistent accuracy in diverse in-the-wild conditions. 3DB estimates the human pose of the body, feet, and hands. It is the first model to use a new parametric mesh representation, Momentum Human Rig (MHR), which decouples skeletal pose and body shape. 3DB employs an encoder–decoder architecture and supports auxiliary prompts, including 2D keypoints and masks, enabling user-guided inference similar to the SAM family of models. We derive high-quality annotations from a multi-stage annotation pipeline that uses various combinations of manual keypoint annotation, differentiable optimization, multi-view geometry, and dense keypoint detection. Our data engine efficiently selects and processes data to ensure data diversity, collecting unusual poses and rare imaging conditions. We present a new evaluation dataset organized by pose and appearance categories, enabling nuanced analysis of model behavior. Our experiments demonstrate superior generalization and substantial improvements over prior methods in both qualitative user preference studies and traditional quantitative analysis. Both 3DB and MHR are open-source.

To address the challenge of short-term object pose tracking in dynamic environments with monocular RGB input, we introduce a large-scale synthetic dataset OmniPose6D, crafted to mirror the diversity of real-world conditions. We additionally present a benchmarking framework for a comprehensive comparison of pose tracking algorithms. We propose a pipeline featuring an uncertainty-aware keypoint refinement network, employing probabilistic modeling to refine pose estimation. Comparative evaluations demonstrate that our approach achieves performance superior to existing baselines on real datasets, underscoring the effectiveness of our synthetic dataset and refinement technique in enhancing tracking precision in dynamic contexts. Our contributions set a new precedent for the development and assessment of object pose tracking methodologies in complex scenes.

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image tokens required for AR models, which constrains both training and inference efficiency, as well as image resolution. To address this, we present Token-Shuffle, a novel yet simple method that reduces the number of image tokens in Transformer. Our key insight is the dimensional redundancy of visual vocabularies in Multimodal Large Language Models (MLLMs), where low-dimensional visual codes from visual encoder are directly mapped to high-dimensional language vocabularies. Leveraging this, we consider two key operations: token-shuffle, which merges spatially local tokens along channel dimension to decrease the input token number, and token-unshuffle, which untangles the inferred tokens after Transformer blocks to restore the spatial arrangement for output. Jointly training with textual prompts, our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis in a unified next-token prediction way while maintaining efficient training and inference. For the first time, we push the boundary of AR text-to-image generation to a resolution of 2048x2048 with gratifying generation performance. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15. Exhaustive large-scale human evaluations also demonstrate our prominent image generation ability in terms of text-alignment, visual flaw, and visual appearance. We hope that Token-Shuffle can serve as a foundational design for efficient high-resolution image generation within MLLMs.

We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of conditional signals (e.g. text, objects, partial sequences). At its core, HOIGPT utilizes a large language model to predict the bidrectional transformation between HOI sequences and natural language descriptions. Given text inputs, HOIGPT generates a sequence of hand and object meshes; given (partial) HOI sequences, HOIGPT generates text descriptions and completes the sequences. To facilitate HOI understanding with a large language model, this paper introduces two key innovations: (1) a novel physically grounded HOI tokenizer, the hand-object decomposed VQ-VAE, for discretizing HOI sequences, and (2) a motion-aware language model trained to process and generate both text and HOI tokens. Extensive experiments demonstrate that HOIGPT sets new state-of-the-art performance on both text generation (+2.01% R Precision) and HOI generation (-2.56 FID) across multiple tasks and benchmarks.

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based architecture forwards N images in a single forward pass, bypassing the need for iterative alignment. Through extensive experiments on camera pose estimation and 3D reconstruction, Fast3R demonstrates state-of-the-art performance, with significant improvements in inference speed and reduced error accumulation. These results establish Fast3R as a robust alternative for multi-view applications, offering enhanced scalability without compromising reconstruction accuracy.

Egocentric videos provide a first-person perspective of the wearer's activities, involving simultaneous interactions with multiple objects. In this work, we propose the task of weakly-supervised Narration-based Video Object Segmentation (NVOS). Given an egocentric video clip and a narration of the wearer's activities, our aim is to segment object instances mentioned in the narration, without using any spatial annotations during training. Existing weakly-supervised video object grounding methods typically yield bounding boxes for referred objects. In contrast, we propose ROSA, a weakly-supervised pixel-level grounding framework learning alignments between referred objects and segmentation mask proposals. Our model harnesses vision-language models pre-trained on image-text pairs to embed region masks and object phrases. During training, we combine (a) a video-narration contrastive loss that implicitly supervises the alignment between regions and phrases, and (b) a region-phrase contrastive loss based on inferred latent alignments. To address the lack of annotated NVOS datasets in egocentric videos, we create a new evaluation benchmark, VISOR-NVOS, leveraging existing annotations of segmentation masks from VISOR alongside 14.6k newly-collected, object-based video clip narrations. Our approach achieves state-of-the-art zero-shot pixel-level grounding performance compared to strong baselines under similar supervision. Additionally, we demonstrate generalization capabilities for zero-shot video object grounding on YouCook2, a third-person instructional video dataset.

3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating part label transfer ability across different object categories. Project website: https://ngailapdi.github.io/projects/3by2/ .

Recovering camera poses from a set of images is a foundational task in 3D computer vision, which powers key applications such as 3D scene/object reconstructions. Classic methods often depend on feature correspondence, such as keypoints, which require the input images to have large overlap and small viewpoint changes. Such requirements present considerable challenges in scenarios with sparse views. Recent data-driven approaches aim to directly output camera poses, either through regressing the 6DoF camera poses or formulating rotation as a probability distribution. However, each approach has its limitations. On one hand, directly regressing the camera poses can be ill-posed, since it assumes a single mode, which is not true under symmetry and leads to sub-optimal solutions. On the other hand, probabilistic approaches are capable of modeling the symmetry ambiguity, yet they sample the entire space of rotation uniformly by brute-force. This leads to an inevitable trade-off between high sample density, which improves model precision, and sample efficiency that determines the runtime. In this paper, we propose ADen to unify the two frameworks by employing a generator and a discriminator: the generator is trained to output multiple hypotheses of 6DoF camera pose to represent a distribution and handle multi-mode ambiguity, and the discriminator is trained to identify the hypothesis that best explains the data. This allows ADen to combine the best of both worlds, achieving substantially higher precision as well as lower runtime than previous methods in empirical evaluations.

Neural Radiance Fields (NeRF) exhibit remarkable performance for Novel View Synthesis (NVS) given a set of 2D images. However, NeRF training requires accurate camera pose for each input view, typically obtained by Structure-from-Motion (SfM) pipelines. Recent works have attempted to relax this constraint, but they still often rely on decent initial poses which they can refine. Here we aim at removing the requirement for pose initialization. We present Incremental CONfidence (ICON), an optimization procedure for training NeRFs from 2D video frames. ICON only assumes smooth camera motion to estimate initial guess for poses. Further, ICON introduces ``confidence": an adaptive measure of model quality used to dynamically reweight gradients. ICON relies on high-confidence poses to learn NeRF, and high-confidence 3D structure (as encoded by NeRF) to learn poses. We show that ICON, without prior pose initialization, achieves superior performance in both CO3D and HO3D versus methods which use SfM pose.

Keypoint detection & descriptors are foundational technologies for computer vision tasks like image matching, 3D reconstruction and visual odometry. Hand-engineered methods like Harris corners, SIFT, and HOG descriptors have been used for decades; more recently, there has been a trend to introduce learning in an attempt to improve keypoint detectors. On inspection however, the results are difficult to interpret; recent learning-based methods employ a vast diversity of experimental setups and design choices: empirical results are often reported using different backbones, protocols, datasets, types of supervisions or tasks. Since these differences are often coupled together, it raises a natural question on what makes a good learned keypoint detector. In this work, we revisit the design of existing keypoint detectors by deconstructing their methodologies and identifying the key components. We re-design each component from first-principle and propose Simple Learned Keypoints (SiLK) that is fully-differentiable, lightweight, and flexible. Despite its simplicity, SiLK advances new state-of-the-art on Detection Repeatability and Homography Estimation tasks on HPatches and 3D Point-Cloud Registration task on ScanNet, and achieves competitive performance to state-of-the-art on camera pose estimation in 2022 Image Matching Challenge and ScanNet.

Visual object tracking is a key component to many egocentric vision problems. However, the full spectrum of challenges of egocentric tracking faced by an embodied AI is underrepresented in many existing datasets; these tend to focus on relatively short, third-person videos. Egocentric video has several distinguishing characteristics from those commonly found in past datasets: frequent large camera motions and hand interactions with objects commonly lead to occlusions or objects exiting the frame, and object appearance can change rapidly due to widely different points of view, scale, or object states. Embodied tracking is also naturally long-term, and being able to consistently (re-)associate objects to their appearances and disappearances over as long as a lifetime is critical. Previous datasets under-emphasize this re-detection problem, and their "framed" nature has led to adoption of various spatiotemporal priors that we find do not necessarily generalize to egocentric video. We thus introduce EgoTracks, a new dataset for long-term egocentric visual object tracking. Sourced from the Ego4D dataset, this new dataset presents a significant challenge to recent state-of-the-art single-object tracking models, which we find score poorly on traditional tracking metrics for our new dataset, compared to popular benchmarks. We further show improvements that can be made to a STARK tracker to significantly increase its performance on egocentric data, resulting in a baseline model we call EgoSTARK. We publicly release our annotations and benchmark, hoping our dataset leads to further advancements in tracking.

Egocentric videos are often available in the form of uninterrupted, uncurated long videos capturing the camera wearers' daily life activities. Understanding these videos requires models to be able to reason about activities, objects, and their interactions. However, current video benchmarks study these problems independently and under short, curated clips. In contrast, real-world applications, e.g. AR assistants, require bundling these problems for both model development and evaluation. In this paper, we propose to study these problems in a joint framework for long video understanding. Our contributions are three-fold. First, we propose an integrated framework, namely Relational Space-Time Query (ReST), for evaluating video understanding models via templated spatiotemporal queries. Second, we introduce two new benchmarks, ReST-ADL and ReST-Ego4D 1 1 The latest version of our benchmark and models will be available here., which augment the existing egocentric video datasets with abundant query annotations generated by the ReST framework. Finally, we present a set of baselines and in-depth analysis on the two benchmarks and provide insights about the query tasks. We view our integrated framework and benchmarks as a step towards comprehensive, multi-step reasoning in long videos, and believe it will facilitate the development of next generations of video understanding models.

Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing. However, the recent success of online methods questions this belief, in particular, for challenging and long video sequences. We understand this work as a rebuttal of those recent observations and an appeal to the community to focus on dedicated near-online VIS approaches. To support our argument, we present a detailed analysis on different processing paradigms and the new end-to-end trainable NOVIS (Near-Online Video Instance Segmentation) method. Our transformer-based model directly predicts spatio-temporal mask volumes for clips of frames and performs instance tracking between clips via overlap embeddings. NOVIS represents the first near-online VIS approach which avoids any handcrafted tracking heuristics. We outperform all existing VIS methods by large margins and provide new state-of-the-art results on both YouTube-VIS (2019/2021) and the OVIS benchmarks.

3D spatial understanding is highly valuable in the context of semantic modeling of environments, agents, and their relationships. Semantic modeling approaches employed on monocular video often ingest outputs from off-the-shelf SLAM/SfM pipelines, which are anecdotally observed to perform poorly or fail completely on some fraction of the videos of interest. These target videos may vary widely in complexity of scenes, activities, camera trajectory, etc. Unfortunately, such semantically-rich video data often comes with no ground-truth 3D information, and in practice it is prohibitively costly or impossible to obtain ground truth reconstructions or camera pose post-hoc. This paper proposes a novel evaluation protocol, Object Reprojection Error (ORE) to benchmark camera trajectories; ORE computes reprojection error for static objects within the video and requires only lightweight object tracklet annotations. These annotations are easy to gather on new or existing video, enabling ORE to be calculated on essentially arbitrary datasets. We show that ORE maintains high rank correlation with standard metrics based on ground truth. Leveraging ORE, we source videos and annotations from Ego4D-EgoTracks, resulting in EgoStatic, a large-scale diverse dataset for evaluating camera trajectories in-the-wild.

Understanding the visual world from human perspectives has been a long-standing challenge in computer vision. Egocentric videos exhibit high scene complexity and irregular motion flows compared to typical video understanding tasks. With the egocentric domain in mind, we address the problem of self-supervised, class-agnostic object detection, aiming to locate all objects in a given view, without any annotations or pre-trained weights. Our method, self-supervised object detection from egocentric videos (DEVI), generalizes appearance-based methods to learn features end-to-end that are category-specific and invariant to viewing angle and illumination. Our approach leverages natural human behavior in egocentric perception to sample diverse views of objects for our multi-view and scale-regression losses, and our cluster residual module learns multi-category patches for complex scene understanding. DEVI results in gains up to 4.11% AP 50 , 0.11% AR 1 , 1.32% AR 10 , and 5.03% AR 100 on recent egocentric datasets, while significantly reducing model complexity. We also demonstrate competitive performance on out-of-domain datasets without additional training or fine-tuning.

Video understanding tasks take many forms, from action detection to visual query localization and spatio-temporal grounding of sentences. These tasks differ in the type of inputs (only video, or video-query pair where query is an image region or sentence) and outputs (temporal segments or spatio-temporal tubes). However, at their core they require the same fundamental understanding of the video, i.e., the actors and objects in it, their actions and interactions. So far these tasks have been tackled in isolation with individual, highly specialized architectures, which do not exploit the interplay between tasks. In contrast, in this paper, we present a single, unified model for tackling query-based video understanding in long-form videos. In particular, our model can address all three tasks of the Ego4D Episodic Memory benchmark which entail queries of three different forms: given an egocentric video and a visual, textual or activity query, the goal is to determine when and where the answer can be seen within the video. Our model design is inspired by recent query-based approaches to spatio-temporal grounding, and contains modality-specific query encoders and task-specific sliding window inference that allow multi-task training with diverse input modalities and different structured outputs. We exhaustively analyze relationships among the tasks and illustrate that cross-task learning leads to improved performance on each individual task, as well as the ability to generalize to unseen tasks, such as zero-shot spatial localization of language queries.

Cognitive science has shown that humans perceive videos in terms of events separated by the state changes of dominant subjects. State changes trigger new events and are one of the most useful among the large amount of redundant information perceived. However, previous research focuses on the overall understanding of segments without evaluating the fine-grained status changes inside. In this paper, we introduce a new dataset called Kinetic-GEB+. The dataset consists of over 170k boundaries associated with captions describing status changes in the generic events in 12K videos. Upon this new dataset, we propose three tasks supporting the development of a more fine-grained, robust, and human-like understanding of videos through status changes. We evaluate many representative baselines in our dataset, where we also design a new TPD (Temporal-based Pairwise Difference) Modeling method for visual difference and achieve significant performance improvements. Besides, the results show there are still formidable challenges for current methods in the utilization of different granularities, representation of visual difference, and the accurate localization of status changes. Further analysis shows that our dataset can drive developing more powerful methods to understand status changes and thus improve video level comprehension. The dataset is available at https://github.com/Yuxuan-W/GEB-Plus.