Papers

Filtered to computer vision · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

48 upvotes · 8 SEP 2026 · Igor Pavlovic, Thiemo Wandel, Anton Obukhov et al.

This paper improves monocular depth estimation models by repurposing image generation models, using a diffusion transformer architecture, to produce sharper and more detailed depth maps that generalize well to out-of-distribution inputs. Practitioners might care about this research because it could lead to better performance in applications such as scene reconstruction and computational photography.

diffusion transformersmonocular depth estimationimage generationcomputer visionimage processing