Single-shot HDR is achieved by conditioning a video diffusion model on an LDR input to generate an exposure bracket and fusing the bracket with per-pixel weights from a lightweight UNet.
a talk at the Stanford Artificial Project in , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
RTPrune introduces a reading-twice inspired two-stage pruning technique for DeepSeek-OCR that retains 84.25% tokens while delivering 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
citing papers explorer
-
Single-Shot HDR Recovery via a Video Diffusion Prior
Single-shot HDR is achieved by conditioning a video diffusion model on an LDR input to generate an exposure bracket and fusing the bracket with per-pixel weights from a lightweight UNet.
-
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
RTPrune introduces a reading-twice inspired two-stage pruning technique for DeepSeek-OCR that retains 84.25% tokens while delivering 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
- Venus-DeFakerOne: Unified Fake Image Detection & Localization