홈 › Papers

DDP: Diffusion Model for Dense Visual Prediction

2023-03-30 · ICCV 2023 1 · Yuanfeng Ji, Zhe Chen, Enze Xie, Lanqing Hong, Xihui Liu, Zhaoqiang Liu, Tong Lu, Zhenguo Li, Ping Luo

We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative paradigm for prediction by progressively removing noise from a random Gaussian distribution, guided by the image. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. Without task-specific design and architecture customization, DDP is easy to generalize to most dense prediction tasks, e.g., semantic segmentation and depth estimation. In addition, DDP shows attractive properties such as dynamic inference and uncertainty awareness, in contrast to previous single-step discriminative methods. We show top results on three representative tasks with six diverse benchmarks, without tricks, DDP achieves state-of-the-art or competitive performance on each task compared to the specialist counterparts. For example, semantic segmentation (83.9 mIoU on Cityscapes), BEV map segmentation (70.6 mIoU on nuScenes), and depth estimation (0.05 REL on KITTI). We hope that our approach will serve as a solid baseline and facilitate future research

📄 PDF Abstract BibTeX arXiv:2303.17559

Code (1)

jiyuanfeng/ddp 공식 구현 pytorch

Tasks

Denoising Depth EstimationmodelMonocular Depth Estimation Prediction Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

2024-09-26 · Jing He, Haodong Li, Wei Yin, Yixun Liang 외

Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the o…

3D Reconstruction Denoising Image Generation Multi-View 3D Reconstruction+2

$\mathrm{D}^\mathrm{3}$-Predictor: Noise-Free Deterministic Diffusion for Dense Prediction

2025-12-08 · Changliang Xia, Chengyou Jia, Minnan Luo, Zhuohang Dang 외 arxiv

Although diffusion models with strong visual priors have emerged as powerful dense prediction backbones, they overlook a core limitation: the stochastic noise at the core of diffusion sampling is inherently misaligned wi…

DPBridge: Latent Diffusion Bridge for Dense Prediction

2024-12-29 · Haorui Ji, Taojun Lin, Hongdong Li

Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks…

Depth Estimation Prediction

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

2026-05-06 · Zhiwei Yang, Pengfei Song, Yucong Meng, Kexue Fu 외 arxiv

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has bee…

Semantic Segmentation

Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Tasks

2025-12-29 · Changgyoon Oh, Jongoh Jeong, Jegyeong Cho, Kuk-Jin Yoon arxiv

Denoising diffusion probabilistic models have brought tremendous advances in generative tasks, achieving state-of-the-art performance thus far. Current diffusion model-based applications exploit the power of learned visu…

parameter-efficient fine-tuning Few-Shot Learning