7 papers
Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework
Pan Liao, Feng Yang, Di Wu +3
Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding. However, existing paradigms predominantly rely on clo…
SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers
Minghao Yin, Jiahao Lu, Wenbo Hu +3
Video diffusion transformers address their tokens by position on the pixel-time grid: an address in the tensor, not in the world. The address we would want, the world point a token…
MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
Jiale Xu, Wang Zhao, Ying Shan
Autoregressive mesh generation has gained attention by tokenizing meshes into sequences and training models in a language-modeling fashion. However, existing approaches suffer from…
Pixal3D: Pixel-Aligned 3D Generation from Images
Dong-Yang Li, Wang Zhao, Yuxin Chen +5
Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity, which…
DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
Yue-Jiang Dong, Wang Zhao, Jiale Xu +2
Diffusion-based video depth estimation methods have achieved remarkable success with strong generalization ability. However, predicting depth for long videos remains challenging. E…
Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
Wang Zhao, Yan-Pei Cao, Jiale Xu +2
We present Assembler, a scalable and generalizable framework for 3D part assembly that reconstructs complete objects from input part meshes and a reference image. Unlike prior appr…