Paper
LLMs & Texto
Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching
Lite Any Stereo V2 (LAS2) presents an efficient stereo matching approach that achieves state-of-the-art accuracy with significantly reduced latency through optimized architecture a…
Hugging Face · Daily Papers
·Junpeng Jing, Ronglai Zuo
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Junpeng Jing, Ronglai Zuo, Zhelun Shen, Shangchen Zhou, Rolandos Alexandros Potamias, Stefanos Zafeiriou
- 3 upvotes da comunidade
- Temas: stereo matching, zero-shot generalization, efficient stereo models, cost aggregation framework, synthetic supervision, self-distillation
Resumo
Resumo original (em inglês), extraído do paper:
Lite Any Stereo V2 (LAS2) presents an efficient stereo matching approach that achieves state-of-the-art accuracy with significantly reduced latency through optimized architecture and training strategies.Onde ler
// relacionados
