We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim illumination, RGB frames often suffer from severe motion blur due to extended exposure times, causing traditional camera pose estimation methods, such as COLMAP, to fail. This results in inaccurate camera pose and blurry color input, compromising the quality of 3D reconstructions. Although recent 3D reconstruction techniques like Neural Radiance Fields and Gaussian Splatting have demonstrated impressive results, they rely on accurate camera trajectory estimation, which becomes challenging under fast motion or poor lighting conditions. Furthermore, rapid camera movement and the limited field of view of depth sensors reduce point cloud overlap, limiting the effectiveness of pose estimation with the ICP algorithm. To address these issues, we introduce a method that combines camera pose estimation and image deblurring using a Gaussian Splatting framework, leveraging both 3D Gaussian splats and depth inputs for enhanced scene representation. Our method first aligns consecutive RGB-D frames through optical flow and ICP, then refines camera poses and 3D geometry by adjusting Gaussian positions for optimal depth alignment. To handle motion blur, we model camera movement during exposure and deblur images by comparing the input with a series of sharp, rendered frames. Experiments on a new RGB-D dataset with extreme motion blur show that our method outperforms existing approaches, enabling high-quality reconstructions even in challenging conditions. This approach has broad implications for 3D mapping applications in robotics, autonomous navigation, and augmented reality. Both code and dataset are publicly available on https://github.com/KAIST-VCLAB/gs-extreme-motion-blur.

Omnidirectional cameras are extensively used in various applications to provide a wide field of vision. However, they face a challenge in synthesizing novel views due to the inevitable presence of dynamic objects, including the photographer, in their wide field of view. In this paper, we introduce a new approach called Omnidirectional Local Radiance Fields (OmniLocaIRF) that can render staticonly scene views, removing and inpainting dynamic ob-jects simultaneously. Our approach combines the principles of local radiance fields with the bidirectional optimization of omnidirectional rays. Our input is an omnidirectional video, and we evaluate the mutual observations of the entire angle between the previous and current frames. To reduce ghosting artifacts of dynamic objects and inpaint occlusions, we devise a multi-resolution motion mask pre-diction module. Unlike existing methods that primarily sep-arate dynamic components through the temporal domain, our method uses multi-resolution neural feature planes for precise segmentation, which is more suitable for long 360° videos. Our experiments validate that OmniLocalRF out-performs existing methods in both qualitative and quanti-tative metrics, especially in scenarios with complex real-world scenes. In particular, our approach eliminates the need for manual interaction, such as drawing motion masks by hand and additional pose estimation, making it a highly effective and efficient solution.

We present a method to reconstruct indoor and outdoor static scene geometry and appearance from an omnidirectional video moving in a small circular sweep. This setting is challenging because of the small baseline and large depth ranges, making it difficult to find ray crossings. To better constrain the optimization, we estimate geometry as a signed distance field within a spherical binoctree data structure and use a complementary efficient tree traversal strategy based on a breadth-first search for sampling. Unlike regular grids or trees, the shape of this structure well-matches the camera setting, creating a better memory-quality trade-off. From an initial depth estimate, the binoc-tree is adaptively subdivided throughout the optimization, previous methods use a fixed depth that leaves the scene undersampled. In comparison with three neural optimization methods and two non-neural methods, ours shows de-creased geometry error on average, especially in a detailed scene, while significantly reducing the required number of voxels to represent such details

Dual-pixel photography is monocular RGB-D photography with an ultra-high resolution, enabling many applications in computational photography. However, there are still several challenges to fully utilizing dual-pixel photography. Unlike the conventional stereo pair, the dual pixel exhibits a bidirectional disparity that includes positive and negative values, depending on the focus plane depth in an image. Furthermore, capturing a wide range of dual-pixel disparity requires a shallow depth of field, resulting in a severely blurred image, degrading depth estimation performance. Recently, several data-driven approaches have been proposed to mitigate these two challenges. However, due to the lack of the ground-truth dataset of the dual-pixel disparity, existing data-driven methods estimate either inverse depth or blurriness map. In this work, we propose a self-supervised learning method that learns bidirectional disparity by utilizing the nature of anisotropic blur kernels in dual-pixel photography. We observe that the dual-pixel left/right images have reflective-symmetric anisotropic kernels, so their sum is equivalent to that of a conventional image. We take a self-supervised training approach with the novel kernel-split symmetry loss accounting for the phenomenon. Our method does not rely on a training dataset of dual-pixel disparity that does not exist yet. Our method can estimate a complete disparity map with respect to the focus-plane depth from a dual-pixel image, outperforming the baseline dual-pixel methods.

Omnidirectional cameras have been used widely to better understand surrounding environments. They are often configured as stereo to estimate depth. However, due to the optics of the fish eye lens, conventional epipolar geometry is inapplicable directly to omnidirectional camera images. Intermediate formats of omnidirectional images, such as equirect-angular images, have been used. However, stereo matching performance on these image formats has been lower than the conventional stereo due to severe image distortion near pole regions. In this paper, to address the distortion problem of omnidirectional images, we devise a novel subdivision scheme of a spherical geodesic grid. This enables more isotropic patch sampling of spherical image information in the omnidirectional camera space. By extending the existing equalarc scheme, our spherical geodesic grid is tessellated with an equalepiline subdivision scheme, making the cell sizes and in-between distances as uniform as possible, i.e., the arc length of the spherical grid cell's edges is well regularized. Also, our uniformly tessellated coordinates in a 2D image can be transformed into spherical coordinates via one-to-one mapping, allowing for analytical forward/backward transformation. Our uniform tessellation scheme achieves a higher accuracy of stereo matching than the traditional cylindrical and cubemap-based approaches, reducing the memory footage required for stereo matching by 20%.

Omnidirectional videos capture environmental scenes effectively, but they have rarely been used for geometry reconstruction. In this work, we propose an egocentric 3D reconstruction method that can acquire scene geometry with high accuracy from a short egocentric omnidirectional video. To this end, we first estimate per-frame depth using a spherical disparity network. We then fuse per-frame depth estimates into a novel spherical binoctree data structure that is specifically designed to tolerate spherical depth estimation errors. By subdividing the spherical space into binary tree and octree nodes that represent spherical frustums adaptively, the spherical binoctree effectively enables egocentric surface geometry reconstruction for environmental scenes while simultaneously assigning high-resolution nodes for closely observed surfaces. This allows to reconstruct an entire scene from a short video captured with a small camera trajectory. Experimental results validate the effectiveness and accuracy of our approach for reconstructing the 3D geometry of environmental scenes from short egocentric omnidirectional video inputs. We further demonstrate various applications using a conventional omnidirectional camera, including novel-view synthesis, object insertion, and relighting of scenes using reconstructed 3D models with texture.

A set of cameras with fisheye lenses have been used to capture a wide field of view. The traditional scan-line stereo algorithms based on epipolar geometry are directly inapplicable to this non-pinhole camera setup due to optical characteristics of fisheye lenses; hence, existing complete 360° RGB-D imaging systems have rarely achieved realtime performance yet. In this paper, we introduce an efficient sphere-sweeping stereo that can run directly on multiview fisheye images without requiring additional spherical rectification. Our main contributions are: First, we introduce an adaptive spherical matching method that accounts for each input fisheye camera’s resolving power concerning spherical distortion. Second, we propose a fast inter-scale bilateral cost volume filtering method that refines distance in noisy and textureless regions with optimal complexity of O(n). It enables real-time dense distance estimation while preserving edges. Lastly, the fisheye color and distance images are seamlessly combined into a complete 360° RGB-D image via fast inpainting of the dense distance map. We demonstrate an embedded 360° RGB-D imaging prototype composed of a mobile GPU and four fisheye cameras. Our prototype is capable of capturing complete 360° RGB-D videos with a resolution of two megapixels at 29 fps. Results demonstrate that our real-time method outperforms traditional omnidirectional stereo and learning-based omnidirectional stereo in terms of accuracy and performance.

In order to enable view-dependent appearance synthesis from the light fields of a scene, it is critical to evaluate the geometric relationships between light and view over surfaces in the scene with high accuracy. Perfect diffuse reflectance is commonly assumed to estimate geometry from light fields via multiview stereo. However, this diffuse surface assumption is invalid with real-world objects. Geometry estimated from light fields is severely degraded over specular surfaces. Additional scene-scale 3D scanning based on active illumination could provide reliable geometry, but it is sparse and thus still insufficient to calculate view-dependent appearance, such as specular reflection, in geometry-based view synthesis. In this work, we present a practical solution of inverse rendering to enable view-dependent appearance synthesis, particularly of scene scale. We enhance the scene geometry by eliminating the specular component, thus enforcing photometric consistency. We then estimate spatially-varying parameters of diffuse, specular, and normal components from wide-baseline light fields. To validate our method, we built a wide-baseline light field imaging prototype that consists of 32 machine vision cameras with fisheye lenses of 185 degrees that cover the forward hemispherical appearance of scenes. We captured various indoor scenes, and results validate that our method can estimate scene geometry and reflectance parameters with high accuracy, enabling view-dependent appearance synthesis at scene scale with high fidelity, i.e., specular reflection changes according to a virtual viewpoint.

Fiducial markers have been broadly used to identify objects or embed messages that can be detected by a camera. Primarily, existing detection methods assume that markers are printed on ideally planar surfaces. The size of a message or identification code is limited by the spatial resolution of binary patterns in a marker. Markers often fail to be recognized due to various imaging artifacts of optical/perspective distortion and motion blur. To overcome these limitations, we propose a novel deformable fiducial marker system that consists of three main parts: First, a fiducial marker generator creates a set of free-form color patterns to encode significantly large-scale information in unique visual codes. Second, a differentiable image simulator creates a training dataset of photorealistic scene images with the deformed markers, being rendered during optimization in a differentiable manner. The rendered images include realistic shading with specular reflection, optical distortion, defocus and motion blur, color alteration, imaging noise, and shape deformation of markers. Lastly, a trained marker detector seeks the regions of interest and recognizes multiple marker patterns simultaneously via inverse deformation transformation. The deformable marker creator and detector networks are jointly optimized via the differentiable photorealistic renderer in an end-to-end manner, allowing us to robustly recognize a wide range of deformable markers with high accuracy. Our deformable marker system is capable of decoding 36-bit messages successfully at ~29 fps with severe shape deformation. Results validate that our system significantly outperforms the traditional and data-driven marker methods. Our learning-based marker system opens up new interesting applications of fiducial markers, including cost-effective motion capture of the human body, active 3D scanning using our fiducial markers' array as structured light patterns, and robust augmented reality rendering of virtual objects on dynamic surfaces.