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...
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.
The paper introduces a method for progressively extending the dynamic range of an image by learning to increase it by a single exposure value first, then applying the network recurrently to achieve full HDR reconstruction. The approach is agnostic to input dynamic range, targets a bounded output domain, and utilizes RAW images with adversarial losses to produce realistic results. Memory Replay during backpropagation allows training over multiple inference stages, reducing reconstruction errors and enabling robust recovery of bright highlights in long‑tailed HDR scenes.
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
arXiv:2606. 09056v1 Announce Type: cross Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths.
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views are sparse or target v...
arXiv:2508.15774v2 Announce Type: replace Abstract: Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data...
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. M...
arXiv:2604.06655v2 Announce Type: replace Abstract: Diffusion-based generative video compression offers a promising paradigm for low-bitrate reconstruction, but existing keyframe-based controllable a...
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamic...
WildRelight is the first in-the-wild dataset designed to evaluate single-image relighting models, featuring high-resolution outdoor scenes captured under strictly aligned, temporally varying natural illuminations paired with high-dynamic-range environment maps. The benchmark demonstrates that state-of-the-art models trained on synthetic data suffer severe domain shifts when applied to real-world imagery. Leveraging the dataset’s temporal structure, the authors introduce a physics-guided inference framework combining Diffusion Posterior Sampling with Temporal Sampling-Aware Test-Time Adaptation, enabling synthetic models to self-supervise and align with real-world statistics on-the-fly.