Related papers: Prompt2NeRF-PIL: Fast NeRF Generation via Pretrain…

We present neural radiance fields (NeRF) with templates, dubbed Template-NeRF, for modeling appearance and geometry and generating dense shape correspondences simultaneously among objects of the same category from only multi-view posed…

Recent advances in neural rendering have shown that, albeit slow, implicit compact models can learn a scene's geometries and view-dependent appearances from multiple views. To maintain such a small memory footprint but achieve faster…

The modern computer graphics pipeline can synthesize images at remarkable visual quality; however, it requires well-defined, high-quality 3D content as input. In this work, we explore the use of imperfect 3D content, for instance, obtained…

Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, and modern super-resolution pipelines typically rely on latent tiling to scale to high resolutions. In practice, a single…

Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by the scarcity of real noisy-clean image pairs, which are…

Diffusion models equipped with language models demonstrate excellent controllability in image generation tasks, allowing image processing to adhere to human instructions. However, the lack of diverse instruction-following data hampers the…

Progress in 3D computer vision tasks demands a huge amount of data, yet annotating multi-view images with 3D-consistent annotations, or point clouds with part segmentation is both time-consuming and challenging. This paper introduces…

The advent of novel view synthesis techniques such as NeRF and 3D Gaussian Splatting (3DGS) has enabled learning precise 3D models only from posed monocular images. Although these methods are attractive, they hold two major limitations that…

Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and time-consuming. Current self-supervised and unsupervised approaches typically rely on…

We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of view synthesis - synthesizing photorealistic novel views of…

Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one…

Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera…

Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering"…

In this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present…

The practical use of text-to-image generation has evolved from simple, monolithic models to complex workflows that combine multiple specialized components. While workflow-based approaches can lead to improved image quality, crafting…

Contemporary registration devices for 3D visual information, such as LIDARs and various depth cameras, capture data as 3D point clouds. In turn, such clouds are challenging to be processed due to their size and complexity. Existing methods…

We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models. Our method operates on a top-down image-based representation, and inserts objects iteratively into the scene by…

Generating a 3D point cloud from a single 2D image is of great importance for 3D scene understanding applications. To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either…

We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted…

Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fail to connect the generated outputs and desired target…