3 citations · 3 across the 7 of their papers we have counts for
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…
Seedance 2.0: Advancing Video Generation for World Complexity
Team Seedance, De Chen, Liyang Chen +168
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro…
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…
Coarse-to-fine Task-driven Inpainting for Geoscience Images
Huiming Sun, Jin Ma, Qing Guo +4
The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that a…
ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding
Bingning Wang, Feiyang Lv, Ting Yao +4
Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLE…
Boosting Image Outpainting with Semantic Layout Prediction
Ye Ma, Jin Ma, Min Zhou +4
The objective of image outpainting is to extend image current border and generate new regions based on known ones. Previous methods adopt generative adversarial networks (GANs) to…
Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval
Shanmin Pang, Jin Ma, Jianru Xue +2
Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address de…