We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting a diffusion prior to sparse-view 3D Gaussian Splatting (3DGS) restoration. Rather than pursuing increasingly sophisticated restoration architectures, we identify a more fundamental limitation shared by existing diffusion-based approaches: supervision at independently noised states does not cover those reached during inference.
arXiv:2606. 26778v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs.
By Xuyue Huang, Zhe Chen, Wang Shen, Xiao-Ping Zhang
Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior work addresses this by retraining the diffusion prior on multi-view data; this improves consistency but makes the sampling contribution inseparable from prior quality.
arXiv:2608. 12032v1 Announce Type: cross Abstract: Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow.
By Enhuai Liu, Yunke Wang, Yutong Wang, Changming Sun, Chang Xu
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.
By Xichen Ye, Yifan Wu, Zhikang Xie, Xiangyu Yue, Cheng Jin, Weizhong Zhang
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
By Tingjia Zhang, Bo Chen, Shengzhong Liu, Fan Wu, Guihai Chen
Dense colored LiDAR maps provide accurate city-scale geometry, but lifting them into 3D Gaussian Splatting (3DGS) retains millions of primitives, making the resulting models costly to store, transmit, render, and adapt. Aggressive primitive reduction alleviates this burden, but can remove the local surface support needed for stable novel-view synthesis and downstream geometric use.
Geometry is invariant to viewpoint, which makes any collection of images a redundant encoding of a single 3D state. Existing feed-forward reconstruction models fail to exploit this: per-view methods emit overlapping, unaligned pointmaps that grow linearly with input count, while global-latent methods commit to a fixed, low-resolution output.
arXiv:2607. 28047v1 Announce Type: cross Abstract: Time-varying implicit neural representations (INRs) provide a compact representation of scientific volumes and, for modalities such as dynamic X-ray computed tomography (CT), are often the only practical way to represent the data.
By Alper Sahistan, Haichao Miao, Zhimin Li, Peer-Timo Bremer, Joshua A Levine, Valerio Pascucci
Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally.
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
High-resolution image and video diffusion models, including SD3, FLUX, and recent video diffusion transformers, have substantially improved generative quality but remain expensive at inference time because they repeatedly evaluate attention-heavy denoisers over many sampling steps. We address this inefficiency by exploiting redundancy in intermediate diffusion features rather than changing model weights or retraining.