20 papers
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Tao Xie, Peishan Yang, Yudong Jin +8
This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly r…
Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation
Yifan Zhan, Zhengqing Chen, Qingjie Wang +7
A major challenge in autonomous driving is the "long tail" of safety-critical edge cases, which often emerge from unusual combinations of common traffic elements. Synthesizing thes…
LongStream: Long-Sequence Streaming Autoregressive Visual Geometry
Chong Cheng, Xianda Chen, Tao Xie +5
Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses t…
Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
Yizhao Han, Tianxing Shi, Zhao Wang +6
Autoregressive (AR) architectures have achieved significant successes in LLMs, inspiring explorations for video generation. In LLMs, top-p/top-k sampling strategies work exceptiona…
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Zhijian Shu, Cheng Lin, Tao Xie +8
3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…
DINO-Tok: Adapting DINO for Visual Tokenizers
Mingkai Jia, Mingxiao Li, Zhijian Shu +12
Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and…