arXiv：cs.LG· Karthik Mohan Kumar, Damian Andrysiak, Pedro Antonio Pena, Kunal Tyagi, Rama Harihara·· 3 小时前AI 评分38
DAGS：解耦外观与几何，为冻结图像 DiT 实现时序稳定的生成式渲染
DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering
AI 导读
DAGS 是一种轻量、无注意力机制的解耦外观与几何条件方案，可引导冻结的图像 DiT 生成高保真、高一致且可独立控制的渲染结果。两个小型卷积编码器逐帧计算条件特征，并以逐层逐元素的残差注入图像 token，避免注意力堆叠条件的二次开销。
正文
Abstract:Diffusion transformers (DiTs) generate high-fidelity images from text and image conditions, but their outputs carry large variance and their faithfulness to a desired target depends heavily on how the condition is supplied. We present DAGS, a lightweight, attention-free, disentangled appearance and geometry conditioning scheme that steers a frozen image DiT to produce high-fidelity, highly faithful, and independently controllable renders. Two small convolutional encoders compute conditioning features once per frame and inject them as a learned, per-layer, element-wise residual into the image tokens, avoiding the quadratic cost of stacking conditions through attention. Because control and temporal handling live outside the frozen backbone, we retain its vast pretrained prior and eliminate backbone-overfitting risk. We further add a small recurrent lighting stabilizer and a training-free temporal guidance term that, coupled with our conditioning, elevate a per-frame image model into a streaming renderer. DAGS produces controllable, high-quality renders at a fraction of the compute of path tracing; it is not real-time, trading compute for controllability and quality. On a matched 1-spp + G-buffer input, per-frame DAGS reconstructs +8.6 dB / +10.1 dB PSNR over the real-time denoiser Intel OIDN and the diffusion renderer RGB<->X while being 2.5-8x more temporally stable perceptually (temporal-LPIPS flicker).
| Comments: | 5 pages, 3 figures, 2 tables. Accepted to SIGGRAPH Asia 2026 Technical Communications |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG) |
| ACM classes: | I.3.7; I.3.3; I.2.6 |
| Cite as: | arXiv:2610.02567 [cs.CV] |
| (or arXiv:2610.02567v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02567 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1145/3829339.3847818
DOI(s) linking to related resources |
Submission history
From: Karthik Mohan Kumar [view email]
[v1]
Thu, 1 Oct 2026 22:59:42 UTC (4,759 KB)
来源：arXiv：cs.LG · arxiv.org