Pith. sign in

REVIEW 5 cited by

JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06347 v1 pith:CTD26GZV submitted 2023-10-10 cs.CV

Jingyang Zhang , Shiwei Li , Yuanxun Lu , Tian Fang , David McKinnon , Yanghai Tsin , Long Quan , Yao Yao This is my paper · ORCID
classification cs.CV
keywords densediffusionjointnetbranchdistributiongenerationmodalitynetwork
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce JointNet, a novel neural network architecture for modeling the joint distribution of images and an additional dense modality (e.g., depth maps). JointNet is extended from a pre-trained text-to-image diffusion model, where a copy of the original network is created for the new dense modality branch and is densely connected with the RGB branch. The RGB branch is locked during network fine-tuning, which enables efficient learning of the new modality distribution while maintaining the strong generalization ability of the large-scale pre-trained diffusion model. We demonstrate the effectiveness of JointNet by using RGBD diffusion as an example and through extensive experiments, showcasing its applicability in a variety of applications, including joint RGBD generation, dense depth prediction, depth-conditioned image generation, and coherent tile-based 3D panorama generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Geometry-aware RGB–depth pretraining plus a 1M multi-task panoramic dataset yields a unified in-context 360° generator with stronger FAED and seam consistency than prior methods.

  2. FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A frequency-guided layout-to-image generation framework, FICGen, improves fidelity, layout alignment, and detector trainability on degraded scenes across five benchmarks.

  3. Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

    cs.LG 2026-07 conditional novelty 5.0 of 10

    DiffTilt is a diffusion-guided falsification method that exponentially tilts a joint distribution over environments and executions to amplify rare safety failures, outperforming conditional sampling and often reducing...

  4. Exploring Representation-Aligned Latent Space for Better Generation

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Aligning VAE latents with DINOv2 semantic features improves latent diffusion model image generation on ImageNet by about 15% FID.

  5. Joint Learning of Depth and Appearance for Portrait Image Animation

    cs.CV 2025-01 conditional novelty 5.0 of 10

    A single diffusion model jointly generates portrait RGB images and aligned depth maps, and its fine-tuned variants can estimate depth, edit from depth, relight, and produce audio-driven talking heads with depth.

Pith tools