Search Results for author:
Found 17 papers, 8 papers with code
Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Multi-scale features have been proven highly effective for object detection, and most ConvNet-based object detectors adopt Feature Pyramid Network (FPN) as a basic component for exploiting multi-scale features.
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution
In addition, stochastic noises fed to the generator are employed for unconditional detail generation, which tends to produce unfaithful details that compromise the fidelity of the generated SR image.
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection.
Auto-regressive Image Synthesis with Integrated Quantization
Extensive experiments over multiple conditional image generation tasks show that our method achieves superior diverse image generation performance qualitatively and quantitatively as compared with the state-of-the-art.
VMRF: View Matching Neural Radiance Fields
With the feature transport plan as the guidance, a novel pose calibration technique is designed which rectifies the initially randomized camera poses by predicting relative pose transformations between the pair of rendered and real images.
Towards Counterfactual Image Manipulation via CLIP
In addition, we design a simple yet effective scheme that explicitly maps CLIP embeddings (of target text) to the latent space and fuses them with latent codes for effective latent code optimization and accurate editing.
Marginal Contrastive Correspondence for Guided Image Generation
We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation.
Modulated Contrast for Versatile Image Synthesis
Perceiving the similarity between images has been a long-standing and fundamental problem underlying various visual generation tasks.
Accelerating DETR Convergence via Semantic-Aligned Matching
First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics.
Multimodal Image Synthesis and Editing: A Survey
As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research.
WaveFill: A Wavelet-based Generation Network for Image Inpainting
This paper presents WaveFill, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly.
Bi-level Feature Alignment for Versatile Image Translation and Manipulation
This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence.
Blind Image Super-Resolution via Contrastive Representation Learning
Extensive experiments on synthetic datasets and real images show that the proposed CRL-SR can handle multi-modal and spatially variant degradation effectively under blind settings and it also outperforms state-of-the-art SR methods qualitatively and quantitatively.
Unbalanced Feature Transport for Exemplar-based Image Translation
In addition, we design a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully.
Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
With image-level attention, transformers enable to model long-range dependencies and generate diverse contents with autoregressive modeling of pixel-sequence distributions.
GMLight: Lighting Estimation via Geometric Distribution Approximation
This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.
EMLight: Lighting Estimation via Spherical Distribution Approximation
Motivated by the Earth Mover distance, we design a novel spherical mover's loss that guides to regress light distribution parameters accurately by taking advantage of the subtleties of spherical distribution.
