7 papers
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Xuanyi Liu, Chunan Yu, Deyi Ji +6
Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing frameworks primarily rely on a ``pure evict…
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
Ying Zang, Yidong Han, Chaotao Ding +8
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences whe…
Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes
Chenye Meng, Zejian Li, Zhongni Liu +9
Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is…
Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
Zejian Li, Yize Li, Chenye Meng +7
Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typi…
Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
An Zhao, Shengyuan Zhang, Ling Yang +6
The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with perfo…
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
Zejian Li, Chenye Meng, Yize Li +9
Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in…