HIVE-Diff is an event-conditioned video diffusion framework that reconstructs high‑frame‑rate HDR video from a single low‑dynamic‑range (LDR) reference frame and event data. It separates the task into event‑guided temporal generation and HDR content completion, enabling the creation of multiple HDR frames from one LDR observation. The model is trained on synthetic data and adapted to real events using teacher‑student distillation with LDR‑event sequences as proxy supervision, achieving strong reconstruction quality across synthetic and real datasets.
arXiv:2604.06161v3 Announce Type: replace-cross Abstract: Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance i...
Low-light image enhancement is severely ill-posed when the input frame contains missing structure, saturated noise, and weak local contrast. Event cameras provide asynchronous brightness-change observations with high temporal resolution, but prior works often treat voxel channels as an unordered or static feature stack before fusion, rather than explicitly modeling their within-window temporal evolution, weakening the temporal evidence that makes events useful.
Due to the limited dynamic range of conventional image sensors, captured low dynamic range (LDR) video often suffers from highlight clipping and shadow detail loss, making high-quality high dynamic ra...
arXiv:2609.27274v1 Announce Type: new Abstract: Due to the limited dynamic range of conventional image sensors, captured low dynamic range (LDR) video often suffers from highlight clipping and shadow...
arXiv:2602.19202v3 Announce Type: replace Abstract: Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensit...
arXiv:2609.25803v1 Announce Type: new Abstract: High-rate dense perception in dynamic environments is limited by the low update rate of RGB cameras, as rapid scene changes can occur between frames. E...
arXiv:2611.07665v1 Announce Type: new Abstract: Capturing scenes with extreme motion and high dynamic range is fundamentally constrained by trade-offs among temporal resolution, spatial detail, signa...
arXiv:2609.36929v1 Announce Type: new Abstract: Recent event-based depth estimation methods successfully transfer geometric priors from vision foundation models via cross-modal distillation. However,...
The paper presents a lightweight extension to the Monst3R 4D reconstruction model by adding an event-camera input branch while keeping the rest of the architecture unchanged. Across three benchmark datasets, this RGB‑event fusion reduces absolute relative error by an average of 3.4% compared to the RGB‑only baseline, with the largest gains occurring under high object motion where RGB‑only methods falter. The study demonstrates that incorporating event data can meaningfully improve 4D reconstruction robustness without a full architectural redesign.
The paper presents a framework for converting standard dynamic range (SDR) videos into high dynamic range (HDR) videos using large-scale generative video models. It introduces a Multi-Exposure Video Model (MEVM) that predicts exposure-bracketed linear SDR sequences from a single nonlinear SDR input, and a Video Merging Model (VMM) that fuses these predictions into a high-quality HDR sequence while preserving detail in shadows and highlights. Experiments, qualitative evaluation, and a user study demonstrate robust HDR conversion for casual consumer footage and iconic films, and the approach can be integrated into existing SDR generative video pipelines.
PriorGS is a 3D Gaussian Splatting framework for single‑exposure high dynamic range (HDR) novel view synthesis that uses learned priors to guide HDR reconstruction and camera response function (CRF) estimation. It introduces a 3D base‑gain HDR representation, separating HDR radiance into an LDR base and a 3D gain field, which improves robustness to inconsistencies in pseudo‑HDR targets and enables 3D HDR appearance editing. Experiments show PriorGS outperforms existing baselines in HDR reconstruction quality.
arXiv:2607. 09114v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos.