6 papers · 1 filter
DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting
Qian Wang, Yu Wang, Weiqi Li +4
While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and a…
Multimodal 3D LUT Generation via StatLUT with Statistical Features for Photorealistic Style Transfer
Yifan Wang, Zhixiang Hao, Yu Wang +1
Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existi…
SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
Tongcheng Fang, Hanling Zhang, Ruiqi Xie +8
Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity o…
db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism
Siqi Chen, Ke Hong, Tianchen Zhao +4
Scaling Diffusion Transformer (DiT) inference via sequence parallelism is critical for reducing latency in visual generation, but is severely hampered by workload imbalance when ap…
LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
Lianwei Yang, Haokun Lin, Tianchen Zhao +6
Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image and text-to-video generation. However, their high computational cost and large parameter sizes p…
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
Shuzhou Yang, Yu Wang, Haijie Li +4
Single image-to-3D generation is pivotal for crafting controllable 3D assets. Given its under-constrained nature, we attempt to leverage 3D geometric priors from a novel view diffu…