The field of computer graphics and vision is witnessing significant advancements in inverse rendering and 3D reconstruction. Researchers are exploring innovative methods to improve the efficiency and accuracy of these techniques, enabling applications in various domains such as robotics, computer-aided design, and virtual reality. One of the key directions is the development of novel view synthesis methods that can render high-quality images from sparse views, reducing the need for extensive datasets and computational resources. Another area of focus is the reconstruction of complex scenes, including glossy and transparent objects, which poses significant challenges due to the instability and incorrect overfitting of radiance fields. Noteworthy papers include LaRI, which presents a new method for unseen geometry reasoning from a single image, and RGS-DR, which introduces a novel inverse rendering method for reconstructing and rendering glossy and reflective objects. Additionally, LIRM presents a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second.TransparentGS is also a notable method that achieves fast inverse rendering of transparent objects with Gaussians, addressing the challenges posed by specular reflection and refraction.