SpeeDiff is a latent diffusion model that jointly trains a VAE and diffusion network from scratch, using a Tweedie Pixel Reconstruction loss to prevent latent collapse. The approach allows scaling a transformer‑based architecture and improves representation alignment. Experiments show the SpeeDiff‑XL model trains 140× faster than Vanilla SiT and 61× faster than REPA, achieving an FID of 1.50 on ImageNet 256×256 and 1.53 on 512×512 without guidance.
By Bingliang Zhang, Wenda Chu, Yizhuo Li, Linjie Yang, Yisong Yue, Katherine L. Bouman, Yang Song, Qiushan Guo
PatchScene is a diffusion-based framework that completes large-scale LiDAR scenes using a patch-based voxel diffusion paradigm, generating fine-grained geometry in localized 3D regions. It incorporates a confidence-guided spatio-temporal fusion mechanism to merge overlapping patches and adjacent frames, and introduces an Annular-Flow diffusion strategy that propagates high-fidelity information from near to far ranges. Experiments on SemanticKITTI show state-of-the-art performance, with the model trained on 20 m LiDAR ranges generalizing to 50 m scenes without retraining.
By Qingdong Xu, Jiajun Zhu, Shilin Zhu, Xinjing He, Chao Lu, Huanran Wang, Jiyao Zhang
We present Scalable Pixel-anchored End-to-end Diffusion (SpeeDiff), a latent diffusion method that jointly trains the VAE and the diffusion model from scratch. In principle, joint training allows the...
arXiv:2602. 13357v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure.
By Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu
arXiv:2607.10495v2 Announce Type: replace
Abstract: Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom oper...
By Filip Pawlicki, Marcel Ka\'ndu{\l}a, Marcin Pucek, Kamil Dobies
arXiv:2607. 14898v1 Announce Type: cross Abstract: Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video.
By Minguk Kang, Suha Kwak
arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.
By Renbiao Jin, Mingxin Yang, Yutian Chen, Junhao Zhuang, Xin Cai, Mulin Yu, Linning Xu, Wenxian Yu, Danping Zou, Shi Guo, Tianfan Xue
Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders.
arXiv:2607. 10762v1 Announce Type: cross Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding.
By Sutharsan Mahendran, Darshana Priyasad, Kaushik Roy, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam
LaGen is an autoregressive framework that generates long‑horizon LiDAR scenes frame by frame, using a single‑frame input and bounding‑box conditions to produce high‑fidelity 4D scenes. It introduces a scene decoupling estimation module for better object‑level interaction and a noise modulation module to reduce error accumulation over time. Evaluations on the nuScenes dataset show that LaGen outperforms existing methods, especially on later frames.
By Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Junjie Li, Juyong Zhang, Yukang Feng, Jianwen Sun, Songbur Wong, Junqi You, Junchi Yan
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly.
arXiv:2609.23153v1 Announce Type: new
Abstract: Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}:...
By Yuxi Liu, Haoyu Li, Zekun Zhang, Tengxu Sun, Yixiang Cai, Jiayong Li, Yifei Xia, Tianle Liu, Baole Ai, Ang Wang, Jiamang Wang, Lin Qu, Kai Zhang, Kun Yuan, Bin Cui