paper-with-me

홈 › Papers

Enhancing Photorealism Enhancement

2021-05-10 · Stephan R. Richter, Hassan Abu Alhaija, Vladlen Koltun

We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The network is trained via a novel adversarial objective, which provides strong supervision at multiple perceptual levels. We analyze scene layout distributions in commonly used datasets and find that they differ in important ways. We hypothesize that this is one of the causes of strong artifacts that can be observed in the results of many prior methods. To address this we propose a new strategy for sampling image patches during training. We also introduce multiple architectural improvements in the deep network modules used for photorealism enhancement. We confirm the benefits of our contributions in controlled experiments and report substantial gains in stability and realism in comparison to recent image-to-image translation methods and a variety of other baselines.

📄 PDF Abstract BibTeX arXiv:2105.04619

Code (2)

isl-org/PhotorealismEnhancement 공식 구현 pytorch
stefanos50/CARLA2Real pytorch

Tasks

Image-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework

2025-08-23 · Stefanos Pasios, Nikos Nikolaidis arxiv

Photorealism is an important aspect of modern video games since it can shape player experience and impact immersion, narrative engagement, and visual fidelity. To achieve photorealism, beyond traditional rendering pipeli…

Image-to-Image Translation

HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement in Game Engines

2026-03-11 · Stefanos Pasios, Nikos Nikolaidis arxiv

Generative models are increasingly used in video game engines to enhance the photorealism of rendered images for visual synthetic data generation and simulation applications. However, they often introduce artifacts that …

Image-to-Image TranslationSynthetic Data Generation

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

2025-11-18 · Yifan Wang, Liya Ji, Zhanghan Ke, Harry Yang 외 arxiv

We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a zero-shot framework that focuses on pres…

Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics

2026-05-20 · Yunlong Wang, Jinjin Shi, Wenbin Gao, Xuran Xu 외 arxiv

Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is…

Image Generation

DREAM: A Benchmark Study for Deepfake photoREalism AssessMent

2025-10-11 · Bo Peng, Zichuan Wang, Sheng Yu, Xiaochuan Jin 외 arxiv

Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem of deepfake detection that aims to relia…

DeepFake Detection