Michael Niemeyer
YOU?
Author Swipe
View article: OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting Open
Sparse-view novel view synthesis is fundamentally ill-posed due to severe geometric ambiguity. Current methods are caught in a trade-off: regressive models are geometrically faithful but incomplete, whereas generative models can complete s…
View article: CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis Open
Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in world modeling, as they only support a fixed number of views an…
View article: GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting
GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting Open
3D scene reconstruction and understanding have gained increasing popularity, yet existing methods still struggle to capture fine-grained, language-aware 3D representations from 2D images. In this paper, we present GALA, a novel framework f…
View article: SuperGSeg: Open-Vocabulary 3D Segmentation with Structured\n Super-Gaussians
SuperGSeg: Open-Vocabulary 3D Segmentation with Structured\n Super-Gaussians Open
3D Gaussian Splatting has recently gained traction for its efficient training\nand real-time rendering. While the vanilla Gaussian Splatting representation is\nmainly designed for view synthesis, more recent works investigated how to\nexte…
View article: Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes
Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes Open
State-of-the-art novel view synthesis methods achieve impressive results for multi-view captures of static 3D scenes. However, the reconstructed scenes still lack "liveliness," a key component for creating engaging 3D experiences. Recently…
View article: MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction Open
Accurate meshing from monocular images remains a key challenge in 3D vision. While state-of-the-art 3D Gaussian Splatting (3DGS) methods excel at synthesizing photorealistic novel views through rasterization-based rendering, their reliance…
View article: Evolutive Rendering Models
Evolutive Rendering Models Open
The landscape of computer graphics has undergone significant transformations with the recent advances of differentiable rendering models. These rendering models often rely on heuristic designs that may not fully align with the final render…
View article: Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians Open
3D Gaussian Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous Localization and Mapping (SLAM), as it provides a compact dense map representation while enabling efficient and high-…
View article: Recent Trends in 3D Reconstruction of General Non‐Rigid Scenes
Recent Trends in 3D Reconstruction of General Non‐Rigid Scenes Open
Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie …
View article: OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views Open
Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segme…
View article: Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes Open
Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie …
View article: RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS Open
Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-the-art quality in challenging scenarios such as in-the-wild…
View article: InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes Open
We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes. Based on a user-provided textual description and a 2D bounding box in a reference viewpoint, InseRF generates new objects in 3D s…
View article: UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections Open
Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images. However, reconstructing real-world captures of complex scenes still remains a challenge. Existing generic 3D reconstruction methods often stru…
View article: DNS SLAM: Dense Neural Semantic-Informed SLAM
DNS SLAM: Dense Neural Semantic-Informed SLAM Open
In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods of…
View article: TextMesh: Generation of Realistic 3D Meshes From Text Prompts
TextMesh: Generation of Realistic 3D Meshes From Text Prompts Open
The ability to generate highly realistic 2D images from mere text prompts has recently made huge progress in terms of speed and quality, thanks to the advent of image diffusion models. Naturally, the question arises if this can be also ach…
View article: DreamBooth3D: Subject-Driven Text-to-3D Generation
DreamBooth3D: Subject-Driven Text-to-3D Generation Open
We present DreamBooth3D, an approach to personalize text-to-3D generative models from as few as 3-6 casually captured images of a subject. Our approach combines recent advances in personalizing text-to-image models (DreamBooth) with text-t…
View article: NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM
NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM Open
Neural field-based 3D representations have recently been adopted in many areas including SLAM systems. Current neural SLAM or online mapping systems lead to impressive results in the presence of simple captures, but they rely on a world-ce…
View article: NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes
NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes Open
With the introduction of Neural Radiance Fields (NeRFs), novel view synthesis has recently made a big leap forward. At the core, NeRF proposes that each 3D point can emit radiance, allowing to conduct view synthesis using differentiable vo…
View article: VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids Open
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every sample along each ray leads to slow rendering. Therefore, exist…
View article: MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction Open
In recent years, neural implicit surface reconstruction methods have become popular for multi-view 3D reconstruction. In contrast to traditional multi-view stereo methods, these approaches tend to produce smoother and more complete reconst…
View article: CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields Open
Tremendous progress in deep generative models has led to photorealistic image synthesis. While achieving compelling results, most approaches operate in the two-dimensional image domain, ignoring the three-dimensional nature of our world. S…
View article: RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs Open
Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints w…
View article: Shape As Points: A Differentiable Poisson Solver
Shape As Points: A Differentiable Poisson Solver Open
In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference time and require…
View article: GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields Open
Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle u…
View article: Learning Implicit Surface Light Fields
Learning Implicit Surface Light Fields Open
Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis requ…
View article: GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis Open
While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or o…
View article: Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision
Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision Open
Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering tech…
View article: Convolutional Occupancy Networks
Convolutional Occupancy Networks Open
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not s…
View article: Texture Fields: Learning Texture Representations in Function Space
Texture Fields: Learning Texture Representations in Function Space Open
In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these clo…