CamGeo is a novel framework that improves sparse camera-conditioned image-to-video generation by distilling rich 3D geometric priors into the diffusion backbone, resulting in geometrically consistent…

This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.

The paper presents GrainGS, a dynamic Gaussian framework for scene reconstruction that balances fine-grained motion modeling, structural stability, and compact representation.

The paper introduces PIXIE, a zero-shot framework for estimating 6D pose of an object from an RGB image using only an untextured 3D model.

The paper proposes a novel cross-axis feature fusion architecture and an auxiliary joint-difference prediction task to significantly improve text-based 3D human motion editing by better understanding…

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art re…

This paper introduces FutureSurf, a benchmark and dataset for evaluating dynamic-scene reconstruction methods' ability to predict future surface geometry.

SimuScene introduces a novel compositional 3D reconstruction pipeline that integrates physics simulation directly into the shape and layout estimation process to generate stable, simulation-ready 3D s…

This paper introduces InFlux++, a large-scale synthetic and real-world dataset for training and evaluating per-frame camera intrinsics prediction models.

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on re…

This paper introduces PS-Track, a hierarchical pipeline for point-supervised Multi-Object Tracking (PS-MOT), which addresses spatial ambiguity and identity drift through Temporal-Feedback Prompting (T…

This paper introduces Flex-Forcing, a framework for video generation that enables a model to operate under both bidirectional and autoregressive generation regimes, achieving better video quality and…

This paper introduces Spatially Conditioned Diffusion Policy (SCDP), a single-camera manipulation system that uses end-effector trajectories as visual attention anchors.

Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…