paper-with-me

Papers

Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis

2024-01-17 · Jonghyun Lee, Hansam Cho, Youngjoon Yoo, Seoung Bum Kim, Yonghyun Jeong

Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful, previous works do not account for the specific localization of said attributes extended into the three dimensional plane. In this context, we present a conditional diffusion model that integrates control over three-dimensional object placement with disentangled representations of global stylistic semantics from multiple exemplar images. Specifically, we first introduce \textit{depth disentanglement training} to leverage the relative depth of objects as an estimator, allowing the model to identify the absolute positions of unseen objects through the use of synthetic image triplets. We also introduce \textit{soft guidance}, a method for imposing global semantics onto targeted regions without the use of any additional localization cues. Our integrated framework, \textsc{Compose and Conquer (CnC)}, unifies these techniques to localize multiple conditions in a disentangled manner. We demonstrate that our approach allows perception of objects at varying depths while offering a versatile framework for composing localized objects with different global semantics. Code: https://github.com/tomtom1103/compose-and-conquer/

📄 PDF Abstract BibTeX arXiv:2401.09048

Code (1)

tomtom1103/compose-and-conquer 공식 구현 pytorch

Tasks

DisentanglementImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Composer: Creative and Controllable Image Synthesis with Composable Conditions

2023-02-20 · Lianghua Huang, Di Chen, Yu Liu, Yujun Shen 외

Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability. This work offers a new generation paradigm that allows flexible control of t…

Image ColorizationImage GenerationImage-to-Image TranslationPose Transfer+3

CharCom: Composable Identity Control for Multi-Character Story Illustration

2025-10-11 · Zhongsheng Wang, Ming Lin, Zhedong Lin, Yaser Shakib 외 arxiv

Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves c…

Text-to-Image Generation

SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation

2020-06-01 · CVPR 2020 6 · Lijun Wang, Jianming Zhang, Oliver Wang, Zhe Lin 외

Monocular depth estimation is an ill-posed problem, and as such critically relies on scene priors and semantics. Due to its complexity, we propose a deep neural network model based on a semantic divide-and-conquer approa…

DecoderDepth EstimationDepth PredictionMonocular Depth Estimation+1

ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion

2025-09-22 · Zichao Hu, Chen Tang, Michael J. Munje, Yifeng Zhu 외 arxiv

This paper considers the problem of enabling robots to navigate dynamic environments while following instructions. The challenge lies in the combinatorial nature of instruction specifications: each instruction can includ…

Reinforcement Learning

Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs

2024-03-07 · Nikhil Mishra, Maximilian Sieb, Pieter Abbeel, Xi Chen

Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult fo…

NeRF