# NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesis

Source: [NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesis](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a1a7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T07:03:33.673Z

Authors: Yixuan Ren, Hanyu Wang, Hao Chen, Bo He, Abhinav Shrivastava

Published: 2025-09-29T06:53:08.000Z

## Abstract

We present NeRV-Diffusion, an implicit latent video diffusion model that synthesizes videos via generating neural network weights. The generated weights can be rearranged as the parameters of a convolutional neural network, which forms an implicit neural representation (INR), and decodes into videos with frame indices as the input. Our framework consists of two stages: 1) A hypernetworkbased tokenizer that encodes raw videos from pixel space to neural parameter space, where the bottleneck latent serves as INR weights to decode. 2) An implicit diffusion transformer that denoises on the latent INR weights. In contrast to traditional video tokenizers that encode videos into frame-wise feature maps, NeRV-Diffusion compresses and generates a video holistically as a unified neural network. This enables efficient and high-quality video synthesis via obviating temporal cross-frame attentions in the denoiser and decoding video latent with dedicated decoders. To achieve Gaussian-distributed INR weights with high expressiveness, we reuse the bottleneck latent across all NeRV layers, as well as reform its weight assignment, upsampling connection and input coordinates. We also introduce SNR-adaptive loss weighting and scheduled sampling for effective training of the implicit diffusion model. NeRV-Diffusion reaches superior video generation quality over previous INR-based models and comparable performance to most recent state-of-the-art non-implicit models on real-world video benchmarks including UCF-101 and Kinetics-600. It also brings a smooth INR weight space that facilitates seamless interpolations between frames or videos.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.24353>)

[PDF](<https://arxiv.org/pdf/2509.24353.pdf>)
