FilterFusion is a lightweight video denoising framework that blends temporally-aware learned features with a small bank of classical denoising filters. It uses a low-cost guidance signal to adaptively mix filter responses at the original resolution, achieving high quality on real sensor noise datasets while keeping the model to only 109K parameters. The approach delivers real‑time performance (55.9 FPS on a single CPU thread) and outperforms lightweight CNN baselines by a large margin in both speed and efficiency.
arXiv:2512.23709v3 Announce Type: replace Abstract: Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due...
arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.
The paper presents a zero‑shot framework for high‑throughput generative video super‑resolution (VSR) that operates on a single high‑end consumer GPU without retraining. It decouples spatial upscaling, handled by a time‑distilled one‑step diffusion backbone, from temporal stabilization, achieved with a lightweight pretrained flow‑based interpolator. A resolution‑aware hybrid attention scheme replaces high‑resolution global attention with neighborhood attention to improve scalability, achieving up to ~32 FPS at 720p and a 44% speedup at 4K on an NVIDIA RTX 4090, while maintaining competitive perceptual quality and temporal consistency on standard VSR benchmarks.
arXiv:2608. 14706v1 Announce Type: cross Abstract: Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data.
ForcingBooster is a framework that adaptively allocates denoising steps to individual video patches in autoregressive diffusion models, allowing easy patches to stop early while difficult patches receive more refinement. This dynamic scheduling reduces the total number of denoising steps by about 50% and improves generation efficiency with negligible quality loss. The method requires only a lightweight routing module and works with most existing few‑step autoregressive diffusion models.
Manifold4D introduces a new denoising strategy for video re‑shooting that injects a rendered point‑cloud directly into the initial noise manifold, eliminating the need for the render to be an explicit conditioning stream during denoising. This approach allows the network to rely solely on the source video as a visual condition, improving camera‑control accuracy on the DAVIS‑Traj benchmark and Vista4D set, with significant reductions in rotation and translation errors while maintaining video fidelity. User studies confirm enhanced trajectory following and dynamic consistency, especially for large yaw amplitudes and even when the render is corrupted.
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
arXiv:2608. 05237v1 Announce Type: cross Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame.
LRConv-NeRV introduces low‑rank separable convolutions into the NeRV neural video decoder, replacing selected dense 3x3 layers to reduce computational load and memory usage. By applying low‑rank factorization progressively from the largest to earlier decoder stages, the method offers controllable trade‑offs between reconstruction quality and efficiency. Experiments show that applying LRConv only to the final decoder stage cuts decoder complexity by 68% and model size by 9.3% with negligible quality loss, while INT8 quantization preserves performance close to the dense baseline.
The paper introduces DeepBM3D, a fully differentiable neural network that emulates the collaborative filtering strategy of BM3D for image denoising. It integrates non‑local patch grouping, DCT‑domain filtering with learned Wiener weights, and multi‑stage refinement, guided by lightweight convolutional feature extractors. Experiments demonstrate that DeepBM3D outperforms classical and hybrid baselines, competes with FFDNet at low to moderate noise levels, and excels on images with repetitive textures.
arXiv:2607. 01962v1 Announce Type: cross Abstract: We study the challenging problem of novel view video synthesis from single images or monocular videos.
arXiv:2608.30782v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realis...