FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering

• URL: http://arxiv.org/abs/2512.16670v1
• Date: Thu, 18 Dec 2025 15:41:08 GMT
• Title: FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering
• Authors: Ole Beisswenger, Jan-Niklas Dihlmann, Hendrik P. A. Lensch,
• Abstract summary: We introduce FrameDiffuser, an autoregressive neural rendering framework that generates temporally consistent, photorealistic frames by conditioning on G-buffer data.<n>We specialize our model to individual environments, prioritizing consistency and inference speed over broad generalization.
• Score: 7.4570191712029965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural rendering for interactive applications requires translating geometric and material properties (G-buffer) to photorealistic images with realistic lighting on a frame-by-frame basis. While recent diffusion-based approaches show promise for G-buffer-conditioned image synthesis, they face critical limitations: single-image models like RGBX generate frames independently without temporal consistency, while video models like DiffusionRenderer are too computationally expensive for most consumer gaming sets ups and require complete sequences upfront, making them unsuitable for interactive applications where future frames depend on user input. We introduce FrameDiffuser, an autoregressive neural rendering framework that generates temporally consistent, photorealistic frames by conditioning on G-buffer data and the models own previous output. After an initial frame, FrameDiffuser operates purely on incoming G-buffer data, comprising geometry, materials, and surface properties, while using its previously generated frame for temporal guidance, maintaining stable, temporal consistent generation over hundreds to thousands of frames. Our dual-conditioning architecture combines ControlNet for structural guidance with ControlLoRA for temporal coherence. A three-stage training strategy enables stable autoregressive generation. We specialize our model to individual environments, prioritizing consistency and inference speed over broad generalization, demonstrating that environment-specific training achieves superior photorealistic quality with accurate lighting, shadows, and reflections compared to generalized approaches.

Related papers

• Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models [34.131515004434846]
  We introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient approach for adapting pretrained video diffusion models to conditional generation tasks.<n>TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples.<n>We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B.
  arXiv  Detail & Related papers  (2025-06-01T12:57:43Z)
• Generative Inbetweening through Frame-wise Conditions-Driven Video Generation [63.43583844248389]
  generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input.<n>We propose a Frame-wise Conditions-driven Video Generation (FCVG) method that significantly enhances the temporal stability of interpolated video frames.<n>Our FCVG demonstrates the capability to generate temporally stable videos using both linear and non-linear curves.
  arXiv  Detail & Related papers  (2024-12-16T13:19:41Z)
• GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering [14.496161390319065]
  We propose GFFE, with a novel framework and an efficient neural network, to generate new frames in real-time without introducing additional latency. We analyze the motion of dynamic fragments and different types of disocclusions, and design the corresponding modules. After filling disocclusions, a light-weight shading correction network is used to correct shading and improve overall quality.
  arXiv  Detail & Related papers  (2024-05-23T18:35:26Z)
• RIGID: Recurrent GAN Inversion and Editing of Real Face Videos [73.97520691413006]
  GAN inversion is indispensable for applying the powerful editability of GAN to real images. Existing methods invert video frames individually often leading to undesired inconsistent results over time. We propose a unified recurrent framework, named textbfRecurrent vtextbfIdeo textbfGAN textbfInversion and etextbfDiting (RIGID) Our framework learns the inherent coherence between input frames in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-08-11T12:17:24Z)
• Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation [93.18163456287164]
  This paper proposes a novel text-guided video-to-video translation framework to adapt image models to videos. Our framework achieves global style and local texture temporal consistency at a low cost.
  arXiv  Detail & Related papers  (2023-06-13T17:52:23Z)
• Towards Smooth Video Composition [59.134911550142455]
  Video generation requires consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs) We show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality.
  arXiv  Detail & Related papers  (2022-12-14T18:54:13Z)
• Context-Aware Video Reconstruction for Rolling Shutter Cameras [52.28710992548282]
  In this paper, we propose a context-aware GS video reconstruction architecture. We first estimate the bilateral motion field so that the pixels of the two RS frames are warped to a common GS frame. Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames.
  arXiv  Detail & Related papers  (2022-05-25T17:05:47Z)
• TimeLens: Event-based Video Frame Interpolation [54.28139783383213]
  We introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both synthesis-based and flow-based approaches. We show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods.
  arXiv  Detail & Related papers  (2021-06-14T10:33:47Z)
• ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation [38.52446103418748]
  We introduce a novel architecture, Adaptive Latent Attention Network (ALANET), which synthesizes sharp high frame-rate videos. We employ combination of self-attention and cross-attention module between consecutive frames in the latent space to generate optimized representation for each frame. Our method performs favorably against various state-of-the-art approaches, even though we tackle a much more difficult problem.
  arXiv  Detail & Related papers  (2020-08-31T21:11:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.